SPEECH RECOGNITION SYSTEM AND METHOD BASED ON WORD-LEVEL CONVERSION CANDIDATE GENERATION

PROBLEM TO BE SOLVED: To provide a speech recognition system and a speech recognition method based on word-level conversion candidate generation.SOLUTION: The speech recognition system includes: a speech recognition result confirmation unit for, when a word sequence and a conversion candidate word f...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	KOO DONG-HO, LEE SOKO, JEONG TAE-SEONG, KIM HOON
Format:	Patent
Sprache:	eng
Schlagworte:	ACOUSTICS CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING MUSICAL INSTRUMENTS PHYSICS SPEECH ANALYSIS OR SYNTHESIS SPEECH OR AUDIO CODING OR DECODING SPEECH OR VOICE PROCESSING SPEECH RECOGNITION
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	PROBLEM TO BE SOLVED: To provide a speech recognition system and a speech recognition method based on word-level conversion candidate generation.SOLUTION: The speech recognition system includes: a speech recognition result confirmation unit for, when a word sequence and a conversion candidate word for at least one word included in the word sequence are provided as a result of speech recognition, confirming the word sequence and the conversion candidate word via a display device; and a word sequence display unit for displaying the word sequence in which the at least one word is visually distinguishable from other words of the word sequence. When the distinguishably displayed word is selected by a user, the word sequence display unit displays the word sequence by replacing the distinguishably displayed word with the conversion candidate word.